{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FWF47FHDAR2PJRBHUBKPBPLA5G","short_pith_number":"pith:FWF47FHD","schema_version":"1.0","canonical_sha256":"2d8bcf94e30474f4c427a054f0bd60e9b271905fb8a9ca61a1213d9ff81ba11a","source":{"kind":"arxiv","id":"2608.04663","version":1},"attestation_state":"computed","paper":{"title":"Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaditya Mehta, Arya Shah","submitted_at":"2026-08-05T10:21:11Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand. We ask whether a guilt signal can instead be calibrated from human neural and behavioural data and transferred to artificial agents. Using the public SoDec responsibility fMRI dataset (40 participants), we fit a subject-fixed-effects regression of momentary-happiness changes on outcome-type counts and recover a guilt weight as the Partner-negative minus Social-negative contrast ($\\hat{w}=1.118$, Cohen's $d=0.214$). We embed this weight in a two-a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.04663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T10:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"84a12853ef8826d2e2ec16f4edb58c35e0913266ac24e754b9eb21160503874a","abstract_canon_sha256":"261022188b3d9623980ee4c5852629c33049ab8a20539b41066c1ded1cb061d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:46:07.511851Z","signature_b64":"6aqsUDYV/Lf8pTyWvJ5KtoVkDCdh0rpjgXiSFaexij56eeRRGQQWFRD9Sl6cnIARW2DWcRgCiHpiza/9YaY8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8bcf94e30474f4c427a054f0bd60e9b271905fb8a9ca61a1213d9ff81ba11a","last_reissued_at":"2026-08-06T01:46:07.510344Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:46:07.510344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaditya Mehta, Arya Shah","submitted_at":"2026-08-05T10:21:11Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning often adds social terms to individual rewards, yet the scale of those terms is usually chosen by hand. We ask whether a guilt signal can instead be calibrated from human neural and behavioural data and transferred to artificial agents. Using the public SoDec responsibility fMRI dataset (40 participants), we fit a subject-fixed-effects regression of momentary-happiness changes on outcome-type counts and recover a guilt weight as the Partner-negative minus Social-negative contrast ($\\hat{w}=1.118$, Cohen's $d=0.214$). We embed this weight in a two-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04663","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.04663/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.04663","created_at":"2026-08-06T01:46:07.512204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04663v1","created_at":"2026-08-06T01:46:07.512204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04663","created_at":"2026-08-06T01:46:07.512204+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWF47FHDAR2P","created_at":"2026-08-06T01:46:07.512204+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWF47FHDAR2PJRBH","created_at":"2026-08-06T01:46:07.512204+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWF47FHD","created_at":"2026-08-06T01:46:07.512204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G","json":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G.json","graph_json":"https://pith.science/api/pith-number/FWF47FHDAR2PJRBHUBKPBPLA5G/graph.json","events_json":"https://pith.science/api/pith-number/FWF47FHDAR2PJRBHUBKPBPLA5G/events.json","paper":"https://pith.science/paper/FWF47FHD"},"agent_actions":{"view_html":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G","download_json":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G.json","view_paper":"https://pith.science/paper/FWF47FHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04663&json=true","fetch_graph":"https://pith.science/api/pith-number/FWF47FHDAR2PJRBHUBKPBPLA5G/graph.json","fetch_events":"https://pith.science/api/pith-number/FWF47FHDAR2PJRBHUBKPBPLA5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G/action/storage_attestation","attest_author":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G/action/author_attestation","sign_citation":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G/action/citation_signature","submit_replication":"https://pith.science/pith/FWF47FHDAR2PJRBHUBKPBPLA5G/action/replication_record"}},"created_at":"2026-08-06T01:46:07.512204+00:00","updated_at":"2026-08-06T01:46:07.512204+00:00"}